System Design with SystemC
Energy-Aware Optimisation for Run-Time Reconfiguration
FCCM '10 Proceedings of the 2010 18th IEEE Annual International Symposium on Field-Programmable Custom Computing Machines
Peak performance model for a custom precision floating-point dot product on FPGAs
Euro-Par 2010 Proceedings of the 2010 conference on Parallel processing
A Model for Matrix Multiplication Performance on FPGAs
FPL '11 Proceedings of the 2011 21st International Conference on Field Programmable Logic and Applications
Dynamic Constant Reconfiguration for Explicit Finite Difference Option Pricing
RECONFIG '11 Proceedings of the 2011 International Conference on Reconfigurable Computing and FPGAs
Efficient communication for FPGA clusters
ARC'12 Proceedings of the 8th international conference on Reconfigurable Computing: architectures, tools and applications
Power modeling and characteristics of field programmable gate arrays
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Hi-index | 0.00 |
Reconfigurable platforms allow hardware developers to customise their designs for specific applications. However, their adoption involves challenges in understanding and estimating the impact of various design parameters and approaches. This paper proposes a unified framework to model behaviour of reconfigurable systems using an event driven simulation approach. This provides an abstract yet informative method to capture both analytical relationships and empirical parameters of reconfigurable systems. It can be used to help making design decisions or verifying analytical models. We apply this approach to three models of reconfigurable applications to estimate the communication efficiency of networked clusters, and the performance and energy efficiency of runtime reconfigurable designs for software-defined radio and for option pricing in finance. The results show that, through this simulation framework, we can verify the accuracy of analytical models and also obtain practical information that is not provided by analytical models.